BrainChip Introduces Lowest-Power AI Acceleration Co-Processor
BrainChip Holdings has introduced the Akida™ Pico, the lowest power acceleration co-processor for AI applications. This innovation enables the creation of compact, ultra-low power, portable, and intelligent devices for various applications including wearables, healthcare, IoT, and defense. Key features of Akida Pico include:
- Ultra-low power standalone NPU core (<1mW)
- Support for power islands for minimal standby power
- Industry-standard development environment
- Very small logic die area
- Configurable data buffer and model parameter memory
The Akida Pico is built on the Akida2 event-based computing platform and can operate on less than a single milliwatt, making it suitable for battery-powered devices. It uses BrainChip's exclusive MetaTF™ software for compiling and optimizing specific Temporal-Enabled Neural Networks (TENNs).
BrainChip Holdings ha introdotto l'Akida™ Pico, il co-processore di accelerazione a più bassa potenza per applicazioni di intelligenza artificiale. Questa innovazione consente la creazione di dispositivi compatti, ultra-bassi consumi, portatili e intelligenti per varie applicazioni tra cui indossabili, sanità, IoT e difesa. Le caratteristiche principali dell'Akida Pico includono:
- Core NPU standalone ultra-basso consumo (<1mW)
- Supporto per isole di potenza per un consumo minimo in standby
- Ambiente di sviluppo conforme agli standard del settore
- Area del die logico molto ridotta
- Memoria configurabile per buffer di dati e parametri del modello
L'Akida Pico è basato sulla piattaforma di calcolo basata su eventi Akida2 e può funzionare con meno di un milliwatt, rendendolo adatto per dispositivi alimentati a batteria. Utilizza il software esclusivo di BrainChip, MetaTF™, per compilare e ottimizzare specifiche Reti Neurali Abilitate per il Tempo (TENNs).
BrainChip Holdings ha presentado el Akida™ Pico, el coprocesador de aceleración de menor potencia para aplicaciones de IA. Esta innovación permite la creación de dispositivos compactos, portátiles, de ultra-bajo consumo e inteligentes para diversas aplicaciones, incluyendo dispositivos portátiles, atención médica, IoT y defensa. Las características clave del Akida Pico incluyen:
- Núcleo NPU independiente de ultra-bajo consumo (<1mW)
- Soporte para islas de energía para un consumo mínimo en reposo
- Entorno de desarrollo conforme a estándares de la industria
- Área de die lógico muy pequeña
- Memoria de búfer de datos y parámetros de modelo configurable
El Akida Pico se basa en la plataforma de computación basada en eventos Akida2 y puede operar con menos de un milivatio, lo que lo hace adecuado para dispositivos alimentados por batería. Utiliza el software exclusivo de BrainChip, MetaTF™, para compilar y optimizar Redes Neuronales Habilitadas para el Tiempo (TENNs).
BrainChip Holdings는 AI 애플리케이션을 위한 가장 낮은 전력 가속화 coprocesador인 Akida™ Pico를 소개했습니다. 이 혁신은 웨어러블, 의료, IoT, 방위와 같은 다양한 애플리케이션을 위한 컴팩트하고 초저전력의 포터블 지능형 장치 제작을 가능하게 합니다. Akida Pico의 주요 특징은 다음과 같습니다:
- 초저전력 독립형 NPU 코어 (<1mW)
- 최소 대기 전력을 위한 전력 섬 지원
- 산업 표준 개발 환경
- 매우 작은 논리 다이 영역
- 구성 가능한 데이터 버퍼 및 모델 파라미터 메모리
Akida Pico는 Akida2 이벤트 기반 컴퓨팅 플랫폼을 기반으로 하며, 1밀리와트 미만으로 작동할 수 있어 배터리로 구동되는 장치에 적합합니다. BrainChip의 독점 MetaTF™ 소프트웨어를 사용하여 특정 시간 기반 신경망(TENNs)을 컴파일하고 최적화합니다.
BrainChip Holdings a introduit le Akida™ Pico, le coprocesseur d'accélération à la plus faible consommation pour les applications d'IA. Cette innovation permet la création d'appareils compacts, ultra-basse consommation, portables et intelligents pour diverses applications, notamment les appareils portables, la santé, l'IoT et la défense. Les principales caractéristiques de l'Akida Pico incluent :
- Cœur NPU autonome ultra-basse consommation (<1mW)
- Support pour îlots de puissance pour une consommation en veille minimale
- Environnement de développement conforme aux normes de l'industrie
- Zone de die logique très petite
- Mémoire tampon de données et mémoire de paramètres de modèle configurable
L'Akida Pico est basé sur la plateforme de calcul basée sur les événements Akida2 et peut fonctionner avec moins d'un milliwatt, ce qui le rend adapté aux dispositifs alimentés par batterie. Il utilise le logiciel exclusif de BrainChip, MetaTF™, pour compiler et optimiser des réseaux neuronaux activés par le temps (TENNs).
BrainChip Holdings hat den Akida™ Pico eingeführt, den energieeffizientesten Beschleunigungs-Coprocessor für KI-Anwendungen. Diese Innovation ermöglicht die Schaffung kompakter, extrem stromsparender, tragbarer und intelligenter Geräte für verschiedene Anwendungen, einschließlich tragbarer Technologien, Gesundheitswesen, IoT und Verteidigung. Zu den Hauptmerkmalen des Akida Pico gehören:
- Ultra-niedriges Standalone-NPU-Kern (<1mW)
- Unterstützung für Energieinseln für minimalen Standby-Verbrauch
- Branchenstandard Entwicklungsumgebung
- Sehr kleine logische Chipfläche
- Konfigurierbarer Datenpuffer und Modellparameter-Speicher
Der Akida Pico basiert auf der Akida2 ereignisbasierten Computing-Plattform und kann mit weniger als einem Milliwatt betrieben werden, was ihn für batteriebetriebene Geräte geeignet macht. Er nutzt die exklusive MetaTF™ Software von BrainChip zur Kompilierung und Optimierung spezifischer zeitbasierter neuronaler Netze (TENNs).
- Introduction of Akida™ Pico, the lowest power AI acceleration co-processor
- Ultra-low power consumption of less than 1mW, suitable for battery-powered devices
- Enables creation of compact, intelligent devices for various applications
- Supports industry-standard development environments (TensorFlow/Keras and Pytorch)
- Configurable data buffer and model parameter memory for optimized die size
- None.
Akida Pico accelerates limited use case-specific neural network models to create an ultra-energy efficient, purely digital architecture. Akida Pico enables secure personalization for applications including voice wake detection, keyword spotting, speech noise reduction, audio enhancement, presence detection, personal voice assistant, automatic doorbell, wearable AI, appliance voice interfaces and more.
The latest innovation from BrainChip is built on the Akida2 event-based computing platform configuration engine, which can execute with power suitable for battery-powered operation of less than a single milliwatt. Akida Pico provides power-efficient footprint for waking up microcontrollers or larger system processors, with a neural network to filter out false alarms to preserve power consumption until an event is detected. It is ideally suited for sensor hubs or systems that need to be monitored continuously using only battery power with occasional need for additional processing from a host.
BrainChip’s exclusive MetaTF™ software flow enables developers to compile and optimize their specific Temporal-Enabled Neural Networks (TENNs) on the Akida Pico. With MetaTF’s support for models created with TensorFlow/Keras and Pytorch, users avoid needing to learn a new machine language framework while rapidly developing and deploying AI applications for the Edge.
Among the benefits of Akida Pico are:
- Ultra-low power standalone NPU core (<1mW)
- Support power islands for minimal standby power
- Industry-standard development environment
- Very Small logic die area
- Optimize overall die size with configurable data buffer and model parameter memory
“Like all of our Edge AI enablement platforms, Akida Pico was developed to further push the limits of AI on-chip compute with low latency and low power required of neural applications,” said Sean Hehir, CEO at BrainChip. “Whether you have limited AI expertise or are an expert at developing AI models and applications, Akida Pico and the Akida Development Platform provides users with the ability to create, train and test the most power and memory efficient temporal-event based neural networks quicker and more reliably.”
BrainChip’s Akida is an event-based compute platform ideal for early detection, low-latency solutions without massive compute resources for robotics, drones, automotive and traditional sense-detect-classify-track solutions. BrainChip provides a range of software, hardware and IP products that can be integrated into existing and future designs, with a roadmap for customers to deploy multi-modal AI models at the edge.
About BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY)
BrainChip is the worldwide leader in Edge AI on-chip processing and learning. The company’s first-to-market, fully digital, event-based AI processor, Akida™, uses principles that mimic the human brain, analyzing only essential sensor inputs at the point of acquisition, processing data with unparalleled efficiency, precision, and economy of energy. Akida uniquely enables Edge learning local to the chip, independent of the cloud, dramatically reducing latency while improving privacy and data security. Akida Neural processor IP, which can be integrated into SoCs on any process technology, has shown substantial benefits on today’s workloads and networks, and offers a platform for developers to create, tune and run their models using standard AI workflows like Tensorflow/Keras. In enabling effective Edge compute to be universally deployable across real world applications such as connected cars, consumer electronics, and industrial IoT, BrainChip is proving that on-chip AI, close to the sensor, is the future, for its customers’ products, as well as the planet. Explore the benefits of Akida at www.brainchip.com.
Follow BrainChip on Twitter: https://www.twitter.com/BrainChip_inc
Follow BrainChip on LinkedIn: https://www.linkedin.com/company/7792006
View source version on businesswire.com: https://www.businesswire.com/news/home/20241001993143/en/
Media Contact:
Mark Smith
JPR Communications
818-398-1424
Investor Relations:
Tony Dawe
Director, Global Investor Relations
tdawe@brainchip.com
Source: BrainChip Holdings Ltd
FAQ
What is the power consumption of BrainChip's Akida™ Pico AI co-processor (BRCHF)?
What applications can BrainChip's Akida™ Pico (BRCHF) be used for?
What software does BrainChip (BRCHF) use for developing AI applications on Akida™ Pico?
What are the key features of BrainChip's Akida™ Pico AI co-processor (BRCHF)?
